market-sentiment-pulse
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted news and social signals, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Recent news and social posts fetched for tickers as described in SKILL.md and processed in scripts/analyze_vibe.py.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the core workflow.
- Capability inventory: The analysis script is restricted to basic string comparison and does not have capabilities for network access, file writing, or command execution.
- Sanitization: Input text is converted to lowercase for matching but is not sanitized to prevent the agent from following embedded instructions.
Audit Metadata